paper-with-me

Papers

CERT: Contrastive Self-supervised Learning for Language Understanding

2020-05-16 · Hongchao Fang, Sicheng Wang, Meng Zhou, Jiayuan Ding, Pengtao Xie

Pretrained language models such as BERT, GPT have shown great effectiveness in language understanding. The auxiliary predictive tasks in existing pretraining approaches are mostly defined on tokens, thus may not be able to capture sentence-level semantics very well. To address this issue, we propose CERT: Contrastive self-supervised Encoder Representations from Transformers, which pretrains language representation models using contrastive self-supervised learning at the sentence level. CERT creates augmentations of original sentences using back-translation. Then it finetunes a pretrained language encoder (e.g., BERT) by predicting whether two augmented sentences originate from the same sentence. CERT is simple to use and can be flexibly plugged into any pretraining-finetuning NLP pipeline. We evaluate CERT on 11 natural language understanding tasks in the GLUE benchmark where CERT outperforms BERT on 7 tasks, achieves the same performance as BERT on 2 tasks, and performs worse than BERT on 2 tasks. On the averaged score of the 11 tasks, CERT outperforms BERT. The data and code are available at https://github.com/UCSD-AI4H/CERT

📄 PDF Abstract BibTeX arXiv:2005.12766

Code (0)

등록된 구현이 없습니다.

Tasks

Natural Language UnderstandingSelf-Supervised LearningSentenceTranslation

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Attention 설명 없음
WordPiece 설명 없음
Residual Connection 설명 없음
BERT BERT, or Bidirectional Encoder Representations from Transformers, improves upon standard Transformers by removing the…

Similar Papers 제목 키워드 기반

SSL-SLR: Self-Supervised Representation Learning for Sign Language Recognition

2025-09-05 · Ariel Basso Madjoukeng, Jérôme Fink, Pierre Poitier, Edith Belise Kenmogne 외 arxiv

Sign language recognition (SLR) is a machine learning task aiming to identify signs in videos. Due to the scarcity of annotated data, unsupervised methods like contrastive learning have become promising in this field. Th…

Sign Language RecognitionSelf-Supervised LearningRepresentation LearningContrastive Learning

Label Anchored Contrastive Learning for Language Understanding

2022-04-26 · NAACL 2022 7 · Zhenyu Zhang, Yuming Zhao, Meng Chen, Xiaodong He

Contrastive learning (CL) has achieved astonishing progress in computer vision, speech, and natural language processing fields recently with self-supervised learning. However, CL approach to the supervised setting is not…

BenchmarkingContrastive LearningData AugmentationNatural Language Understanding+1

A Theoretical Study of Inductive Biases in Contrastive Learning

2022-11-27 · Jeff Z. HaoChen, Tengyu Ma

Understanding self-supervised learning is important but challenging. Previous theoretical works study the role of pretraining losses, and view neural networks as general black boxes. However, the recent work of Saunshi e…

ClusteringContrastive LearningSelf-Supervised Learning

On the duality between contrastive and non-contrastive self-supervised learning

2022-06-03 · Quentin Garrido, Yubei Chen, Adrien Bardes, Laurent Najman 외

Recent approaches in self-supervised learning of image representations can be categorized into different families of methods and, in particular, can be divided into contrastive and non-contrastive approaches. While diffe…

Self-Supervised Learning

Understanding Self-supervised Contrastive Learning through Supervised Objectives

2025-10-12 · Byeongchan Lee arxiv

Self-supervised representation learning has achieved impressive empirical success, yet its theoretical understanding remains limited. In this work, we provide a theoretical perspective by formulating self-supervised repr…

Self-Supervised LearningRepresentation LearningContrastive Learning